Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2308 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1557. Min Range: -6.1557
Max Act: 6.1557. Min Act: -0.1700
Data Index: 4961297 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1557. Min Range: -6.1557
Max Act: 5.9057. Min Act: -0.1700
Data Index: 7779995 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1557. Min Range: -6.1557
Max Act: 5.6557. Min Act: -0.1700
Data Index: 8777533 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1557. Min Range: -6.1557
Max Act: 5.5620. Min Act: -0.1700
Data Index: 6097541 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1557. Min Range: -6.1557
Max Act: 5.4682. Min Act: -0.1700
Data Index: 1982340 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1557. Min Range: -6.1557
Max Act: 5.3745. Min Act: -0.1700
Data Index: 2201415 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1557. Min Range: -6.1557
Max Act: 5.3432. Min Act: -0.1700
Data Index: 1998285 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1557. Min Range: -6.1557
Max Act: 5.2807. Min Act: -0.1700
Data Index: 7516817 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1557. Min Range: -6.1557
Max Act: 5.1870. Min Act: -0.1700
Data Index: 2082792 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1557. Min Range: -6.1557
Max Act: 5.1870. Min Act: -0.1700
Data Index: 9401 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1557. Min Range: -6.1557
Max Act: 5.1870. Min Act: -0.1700
Data Index: 1336622 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1557. Min Range: -6.1557
Max Act: 5.1245. Min Act: -0.1700
Data Index: 2097989 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1557. Min Range: -6.1557
Max Act: 5.0932. Min Act: -0.1700
Data Index: 4560319 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1557. Min Range: -6.1557
Max Act: 5.1245. Min Act: -0.1700
Data Index: 4992690 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1557. Min Range: -6.1557
Max Act: 5.0620. Min Act: -0.1700
Data Index: 1828661 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1557. Min Range: -6.1557
Max Act: 5.0932. Min Act: -0.1700
Data Index: 7424165 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1557. Min Range: -6.1557
Max Act: 5.0932. Min Act: -0.1700
Data Index: 974184 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1557. Min Range: -6.1557
Max Act: 5.0620. Min Act: -0.1700
Data Index: 3722284 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1557. Min Range: -6.1557
Max Act: 5.0620. Min Act: -0.1700
Data Index: 3274669 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1557. Min Range: -6.1557
Max Act: 5.0307. Min Act: -0.1700
Data Index: 3424084 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #19